I learn R language since decade and finish my first research which was a backtest on the soccer betting. Today I tried to summarise it. Below two links are my research and submitted for the contest.
I collected the pre-match odds price (open and close price) of 1x2 of 40 bookmakers, 29 bookmakers among them have Asian-Handicap and Over-Under via soccer betting information website.
I collected the Asian-Handicap and Over-Under odds price (whole price movement from open price until close price) of 13 bookmakers.
I used the Dimitris Karlis and Ioannis Ntzoufras (2005) and then fit the weighted function from Mark Dixon and Stuart Coles (1996) into it. All research are using Markov-Chain method to test every single match in 3 years soccer seasons. However, my model using 1st season to model for 2nd season, and then based on the Mavkov basic model in 2nd season to measure the weighted function, only the 3rd season started a weighted model, therefore 2 soccer season dataset required in order to predict coming soccer match.
There are 4 soccer seasons dataset and 1st and 2nd seasons is the datasets for modelling. The staking model started from 3rd season to 4th season.
There has few adjustment onto the model. - A constant weighted function over over whole moving windows for a soccer season based on last soccer season - A weekly constant Markov-Chain weighted function - A daily constant Markov-Chain weighted function - An observation dynamic weighed function
Secondly, due to constrant restricted on to the model, I tried to compare (Might similar with hidden factor for the Markov Chain).
https://issuu.com/englianhu/docs/odds_modelling_and_testing_ineffici
Finally the model with below adjustment came with highest ROI.
I took below probability as the baseline of bookmakers. After that applied a full Kelly Criterion betting model.
Due to the paper above using the normal betting strategy by refer to Mark Dixon and Stuart Coles (1996) is not profitable, here I try to use Kelly Criterion (staking on 13 bookmakers) and the ROI was outperformed.
|No|Category|With Spreads (2011/12)|Ratio (%)|Without Spreads (2011/12)|Ratio (%)|With Spreads (2012/13)|Ratio (%)|Without Spreads (2012/13)|Ratio (%)| |---|---|---|---|---|---|---|---|---|---| |1|No of Matches|4,896|1|4,896|1|5,514|1|5,514|1| |2|Total PL|$353.96966|55.57%|$381.06299|53.98%|$448.8993|59.35%|$488.91841|58.60%| |3|No of Bets|2,268|46.32%|2,404|49.10%|2,570|46.61%|2,697|48.91%| |4|No of Won Bets|1,531|31.27%|1,584|32.35%|1,765|32.01%|1,824|33.08%| |5|No of Voided Bets|128|2.61%|143|2.92%|192|3.48%|196|3.55%| |6|No of Lose Bets|609|12.44%|677|13.83%|613|11.12%|677|12.28%| |7|Staking|$636.98372|1|$705.89203|1|$756.2979|1|$834.32032|1| |8|Won Bets Stakes|$453.43724|71.19%|$496.09555|70.28%|$563.6685|74.53%|$614.24795|73.62%| |9|Voided Stakes|$19.13296|3.00%|$22.67241|3.21%|$27.1151|3.59%|$32.12999|3.85%| |10|Lose Bets Stakes|-$99.46758|-15.62%|-$115.03256|-16.30%|-$114.7691|-15.18%|-$125.32954|-15.02%|
table 4.1 : Staking breakdown and result of the bets settlement.
|Company|PL (2011/12)|Ratio (%)|PL2 (2011/12)|Ratio (%)|PL (2012/13)|Ratio (%)|PL2 (2012/13)|Ratio (%)| | --- | --- | --- | --- | --- | --- | --- | --- | --- | |Ladbrokes|$33.772411|9.54%|$38.25184|10.04%|$44.53507895|9.92%|$46.7763362|9.57%| |Bet365|$34.120624|9.64%|$37.19263|9.76%|$33.53743752|7.47%|$40.6766948|8.32%| |Macauslot|$35.740062|10.10%|$40.23454|10.56%|$1.76408658|0.39%|$1.9329171|0.40%| |X10Bet|$37.538487|10.61%|$41.64034|10.93%|$33.62892077|7.49%|$40.6921976|8.32%| |X188Bet|$36.579289|10.33%|$38.25589|10.04%|$41.05668234|9.15%|$46.1156378|9.43%| |SBOBET|$40.392461|11.41%|$41.90898|11.00%|$43.50915478|9.69%|$47.8308212|9.78%| |Mansion88|$31.219547|8.82%|$32.38999|8.50%|$42.44403404|9.46%|$43.9521665|8.99%| |YSB88|$13.167746|3.72%|$14.34128|3.76%|$45.92688667|10.23%|$46.8393963|9.58%| |X12BET|$36.802466|10.40%|$38.19015|10.02%|$36.03065656|8.03%|$36.2449956|7.41%| |VictorChandler|$24.391917|6.89%|$25.95763|6.81%|$45.13420638|10.05%|$46.2154620|9.45%| |Canbet|$10.347393|2.92%|$10.97516|2.88%|$41.04019224|9.14%|$46.9617659|9.61%| |Betinternet|$10.286812|2.91%|$11.18731|2.94%|$40.20594752|8.96%|$44.5435274|9.11%| |Titanbet|$9.610441|2.72%|$10.53726|2.77%|$0.08604952|0.02%|$0.1364944|0.03%|
table 4.2 : Breakdown of Operators - Profit & Loss on the Odds Price with/without Overrounds.
Finally, the model is proof that profitable. However the odds price was collected from the information website but the from bookmakers website.
Niko Marttinen (2006) introduced a multinormial model which is more accurate than the bivariate poisson model. The bivariate poisson model by Niko Marttinen (2006) added the bookmakers odds price as the hidden effects where I need to upgraded beyond the future.
Powered by - Copyright® Intellectual Property Rights of Scibrokes®個人の経営企業
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.